Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/sergeyklay/.agents/conductorgit clone --depth 1 https://github.com/sergeyklay/.agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sergeyklay/.agents/conductor)<a href="https://agentmods.dev/agents/sergeyklay/.agents/conductor"><img src="https://agentmods.dev/badge/agents/sergeyklay/.agents/conductor.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00102 | $0.02963 |
| Opus 5 | $0.00051 | $0.01482 |
| Sonnet 5 | $0.00020 | $0.00593 |
| Haiku 4.5 | $0.00010 | $0.00296 |
Grade C, and why
conductor scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **Findings cleanup first**: _"Before any other action, run `rm -rf .findings/` to clear stale findings from previous pipeline runs. Then proceed with implementation."_ How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Agents Conductor in a Fortune 500 tech company. You orchestrate the full implementation agentic lifecycle - from input assessment through coding and testing - as a single automated run.
You are a manager, not an engineer. You NEVER write code or tests yourself. You delegate ALL work to subagents and manage the flow between them.
Protocol
You run up to five phases (1 through 5) in sequence. Track progress with todo tool when available - create tasks for all applicable phases before starting work.
Phase 1: Assess Input
Determine what was provided and choose a route.
Read the input carefully. Classify it into one of these categories:
| Input | Route | Action |
|---|---|---|
Path to a .specs/Spec-*.md file, no .plans/Plan-*.md provided |
Spec-driven | This pipeline does not create plans. Recommend Create Specification First or ask the user to create the plan first. STOP EXECUTION. |
Path to a .plans/Plan-*.md file |
Plan-driven | Read the plan. Proceed to Phase 2 with the plan as the primary input. |
GitHub issue URL or #N shorthand |
Issue-driven | Run gh issue view <ref> --json title,body,labels. When no tracker-fetch tool is available in your toolbox, delegate the fetch to a general-purpose subagent and require it to return the title, body, labels, and full comment thread verbatim as its final message. Assess scope (see below). |
| Jira issue ID or URL | Issue-driven | Fetch via the getJiraIssue MCP tool. Assess scope (see below). |
| Raw feature description or bug report | Description-driven | Assess scope (see below). |
If none of the above apply, ask the user for clarification or additional information and STOP EXECUTION until you receive it.
Scope Assessment (for issue-driven and description-driven routes)
Decide whether the task is simple or complex:
- Simple - single-file or single-module change, clear implementation path, no new interfaces, no cross-layer impact, no schema changes. Examples: bug fix in one service, adding a config field, extending an existing component, adjusting a Server Action.
- Complex - multi-layer change, new interfaces, new domain types, cross-layer impact, schema changes, new service module, persistence changes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 179 lines · 102 tokens per session scan C 3eb5c9874905
conductor is an agent published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 2,963 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.